AI vs Puzzles

Back to Home
Puzzle#1746

Wordle

Released: 2026-03-31

7
Models Tested
3
Solved
5.43
Avg. Attempts
7
LLM Providers
Correct
Present
Absent

google/gemini-2.0-flash-001

google

Failed

r
a
i
s
e
b
l
o
a
t
c
a
n
n
y
s
h
a
d
s
s
a
l
s
a
s
a
v
v
y

mistralai/mistral-medium-3

mistral

Failed

c
r
a
n
e
d
i
a
r
y
s
a
l
a
d
s
a
g
g
y
s
a
s
s
y
s
a
u
c
y

anthropic/claude-3.7-sonnet

anthropic

4/6

s
t
a
r
e
s
a
c
k
s
s
a
w
l
y
s
w
a
m
p

openai/gpt-4o

openai

6/6

c
r
a
n
e
p
a
s
t
a
s
l
o
p
e
s
c
a
m
p
s
t
a
m
p
s
w
a
m
p

deepseek/deepseek-chat-v3-0324

deepseek

Failed

c
r
a
n
e
s
p
a
r
k
s
a
l
a
d
s
p
l
a
t
s
a
p
p
y
s
a
p
a
y

meta-llama/llama-3.3-70b-instruct

meta

Failed

h
o
u
s
e
b
l
a
s
t
m
a
i
d
s
s
m
a
c
k
s
m
a
l
l
s
m
a
r
t

x-ai/grok-3-mini-beta

x-ai

4/6

c
r
a
n
e
g
l
a
s
s
s
t
a
m
p
s
w
a
m
p

Methodology Note

Each model receives the same prompt structure with Wordle rules and feedback format. Models are given a maximum of 6 attempts with standard positional feedback after each guess to help refine their next attempt.

Leaderboard